Hugging Face's logo

mlfoundations-dev
/
oh_v3-1_only_evol_instruct_140k

Text Generation
Transformers
Safetensors
llama
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
esfrankel17 commited on
Commit
668a021
•
1 Parent(s): 290d3bb

Training in progress, epoch 1

Browse files
Files changed (5) hide show
  1. model-00001-of-00004.safetensors +1 -1
  2. model-00002-of-00004.safetensors +1 -1
  3. model-00003-of-00004.safetensors +1 -1
  4. model-00004-of-00004.safetensors +1 -1
  5. trainer_log.jsonl +6 -0
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:13d7c6cc3e2ae647125ab326e62bb0bc1ab7a61ba4466fd8e6896e74fd01f7d0
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13a2623575868eb640dc31b06daf2b2b81af60ce077052093f67bbca0a0f04aa
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:63fc749b91ffbe9ebda10e223599d2a06ad83f22b750259e0a471c3a03a9afbc
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db8f0f9b671bbc3f8ec745be129b9ef1c7bd91da0fd3fcef1dc3c82811b9ea31
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:45c24656c3c251b3e344f562c7a509f3094154443624fb3ea535fed02e636157
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b5d6b900533134d629f09b546a63714b508ffd9d056ea1e824ce4081d410f3a
3
  size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ac7b7c2664a9fc34b1b3a38402c32483a9d65190d1fbcf8a2a6605f35ef68815
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02e50ac30cef59aac40f25c10bcace4c01449b29e87aa9da49792d384748e35a
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -3,3 +3,9 @@
3
  {"current_steps": 30, "total_steps": 135, "loss": 0.902, "learning_rate": 5e-06, "epoch": 0.6539509536784741, "percentage": 22.22, "elapsed_time": "0:15:51", "remaining_time": "0:55:30"}
4
  {"current_steps": 40, "total_steps": 135, "loss": 0.8817, "learning_rate": 5e-06, "epoch": 0.8719346049046321, "percentage": 29.63, "elapsed_time": "0:21:05", "remaining_time": "0:50:04"}
5
  {"current_steps": 45, "total_steps": 135, "eval_loss": 0.8728658556938171, "epoch": 0.9809264305177112, "percentage": 33.33, "elapsed_time": "0:24:26", "remaining_time": "0:48:53"}
 
 
 
 
 
 
 
3
  {"current_steps": 30, "total_steps": 135, "loss": 0.902, "learning_rate": 5e-06, "epoch": 0.6539509536784741, "percentage": 22.22, "elapsed_time": "0:15:51", "remaining_time": "0:55:30"}
4
  {"current_steps": 40, "total_steps": 135, "loss": 0.8817, "learning_rate": 5e-06, "epoch": 0.8719346049046321, "percentage": 29.63, "elapsed_time": "0:21:05", "remaining_time": "0:50:04"}
5
  {"current_steps": 45, "total_steps": 135, "eval_loss": 0.8728658556938171, "epoch": 0.9809264305177112, "percentage": 33.33, "elapsed_time": "0:24:26", "remaining_time": "0:48:53"}
6
+ {"current_steps": 50, "total_steps": 135, "loss": 0.9119, "learning_rate": 5e-06, "epoch": 1.1008174386920981, "percentage": 37.04, "elapsed_time": "0:27:50", "remaining_time": "0:47:19"}
7
+ {"current_steps": 60, "total_steps": 135, "loss": 0.8201, "learning_rate": 5e-06, "epoch": 1.318801089918256, "percentage": 44.44, "elapsed_time": "0:33:02", "remaining_time": "0:41:18"}
8
+ {"current_steps": 70, "total_steps": 135, "loss": 0.8167, "learning_rate": 5e-06, "epoch": 1.5367847411444142, "percentage": 51.85, "elapsed_time": "0:38:15", "remaining_time": "0:35:31"}
9
+ {"current_steps": 80, "total_steps": 135, "loss": 0.8136, "learning_rate": 5e-06, "epoch": 1.7547683923705724, "percentage": 59.26, "elapsed_time": "0:43:27", "remaining_time": "0:29:52"}
10
+ {"current_steps": 90, "total_steps": 135, "loss": 0.8115, "learning_rate": 5e-06, "epoch": 1.9727520435967303, "percentage": 66.67, "elapsed_time": "0:48:38", "remaining_time": "0:24:19"}
11
+ {"current_steps": 90, "total_steps": 135, "eval_loss": 0.8485425710678101, "epoch": 1.9727520435967303, "percentage": 66.67, "elapsed_time": "0:49:31", "remaining_time": "0:24:45"}